paper-with-me

홈 › Papers

Private Federated Learning with Autotuned Compression

2023-07-20 · Enayat Ullah, Christopher A. Choquette-Choo, Peter Kairouz, Sewoong Oh

We propose new techniques for reducing communication in private federated learning without the need for setting or tuning compression rates. Our on-the-fly methods automatically adjust the compression rate based on the error induced during training, while maintaining provable privacy guarantees through the use of secure aggregation and differential privacy. Our techniques are provably instance-optimal for mean estimation, meaning that they can adapt to the ``hardness of the problem" with minimal interactivity. We demonstrate the effectiveness of our approach on real-world datasets by achieving favorable compression rates without the need for tuning.

📄 PDF Abstract BibTeX arXiv:2307.10999

Code (1)

google-research/federated 공식 구현 tf

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

SoteriaFL: A Unified Framework for Private Federated Learning with Communication Compression

2022-06-20 · Zhize Li, Haoyu Zhao, Boyue Li, Yuejie Chi

To enable large-scale machine learning in bandwidth-hungry environments such as wireless networks, significant progress has been made recently in designing communication-efficient federated learning algorithms with the a…

Federated LearningPrivacy Preserving

Privacy-Aware Compression for Federated Learning Through Numerical Mechanism Design

2022-11-08 · Chuan Guo, Kamalika Chaudhuri, Pierre Stock, Mike Rabbat

In private federated learning (FL), a server aggregates differentially private updates from a large number of clients in order to train a machine learning model. The main challenge in this setting is balancing privacy wi…

Federated Learning

DP-REC: Private & Communication-Efficient Federated Learning

2021-11-09 · Aleksei Triastcyn, Matthias Reisser, Christos Louizos

Privacy and communication efficiency are important challenges in federated training of neural networks, and combining them is still an open problem. In this work, we develop a method that unifies highly compressed commun…

Federated Learning

An Adaptive PID Autotuner for Multicopters with Experimental Results

2021-09-27 · John Spencer, Joonghyun Lee, Juan Augusto Paredes, Ankit Goel 외

This paper develops an adaptive PID autotuner for multicopters, and presents simulation and experimental results. The autotuner consists of adaptive digital control laws based on retrospective cost adaptive control imple…

Sensitivity

Intrinisic Gradient Compression for Federated Learning

2021-12-05 · Luke Melas-Kyriazi, Franklyn Wang

Federated learning is a rapidly-growing area of research which enables a large number of clients to jointly train a machine learning model on privately-held data. One of the largest barriers to wider adoption of federate…

BIG-bench Machine LearningFederated LearningLearning Theory